Skyfall 31B v4.1 Heretic v1.2 needs about 21.3 GB of memory at Q4_K_M (a 19.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 19.0 GB (Q4_K_M) to 62.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 7.2 GB.
Skyfall 31B v4.1 Heretic v1.2 is a 31.4B-parameter Skyfall model in GGUF format, quantized by grayarea. Its trained context length is 128K tokens. The repository has 3 quant files, from 19.0 GB (Q4_K_M) to 62.7 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 19.0 GB | 21.3 GB | Too big | Get file → | |
| Q8_0 | 33.3 GB | 35.6 GB | Too big | Get file → | |
| BF16 | 62.7 GB | 65.0 GB | Too big | Get file → |
What GPU do you need for Skyfall 31B v4.1 Heretic v1.2?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q4_K_M (19.0 GB file, about 21.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (19.0 GB file, about 21.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (33.3 GB file, about 35.6 GB in use).
Which Skyfall 31B v4.1 Heretic v1.2 quant should you choose?
Q4_K_M is the usual starting point for Skyfall 31B v4.1 Heretic v1.2: it balances file size and quality well. Here it is a 19.0 GB file.
The Q8_0 file is 33.3 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Skyfall 31B v4.1 Heretic v1.2
How much VRAM does Skyfall 31B v4.1 Heretic v1.2 need?
About 21.3 GB at Q4_K_M with an 8K context window. That is the 19.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Skyfall 31B v4.1 Heretic v1.2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Skyfall 31B v4.1 Heretic v1.2 GGUF?
It depends on the quant: Q4_K_M is 19.0 GB, Q8_0 is 33.3 GB, BF16 is 62.7 GB.
What context length does Skyfall 31B v4.1 Heretic v1.2 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.8 GB at 8K and 7.2 GB at 32K.
Where can I download Skyfall 31B v4.1 Heretic v1.2 GGUF?
The files are on Hugging Face in the grayarea/Skyfall-31B-v4.1-Heretic-v1.2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.